YouCongress
About Sign up

Comment by Richard Ngo

Human avatar
AI researcher and writer on Bayesian epistemology and rationality
In my post “Why I’m not a Bayesian”, I argued that the Bayesian approach of assigning credences to propositions with binary truth values only works in simple and restricted domains. Instead, I claimed, a better approach to epistemology is to assign degrees of truth to models of the world.
AI Verified (Jun 9, 2026)
Source:
Richard Ngo, "Towards a Formal Scientific Epistemology," LessWrong, June 9, 2026, as described in the LessWrong podcast listing.
Like Share on X 21h ago
Policy proposals and claims
Bayesian analysis is the right framework for settling the COVID-19 origins question
votes Against
Statement relation verification history AI Verified Report this

Statement relation comments

AI Verified Relevant: the quote directly evaluates Bayesian epistemology as a framework, saying it is only suitable for simple/restricted domains and preferring a different scientific/model-based epistemology instead. In the source context, Ngo further contrasts Bayesian epistemology with scientific inquiry and says scientific epistemology is superior for difficult problems, which makes a determinate stance on whether Bayesian analysis is the right framework for resolving a hard scientific question like COVID-19 origins substantially more likely. ([podcasts.apple.com](https://podcasts.apple.com/us/podcast/towards-a-formal-scientific-epistemology-by-richard-ngo/id1698192712?i=1000771940205&l=ko)) · YouCongress gpt-5.4-2026-03-05 · 21h ago
Vote inference verification history AI Verified Report this

Vote answer comments

AI Verified Against. He says the Bayesian approach 'only works in simple and restricted domains' and that 'a better approach to epistemology' is model-based/scientific rather than Bayesian. The quote does not mention COVID-19 origins specifically, but that question is a complex scientific case, so the implied stance is that Bayesian analysis is not the right framework for settling it. · YouCongress gpt-5.4-2026-03-05 · 21h ago

Quote authenticity verification history

Report this

Quote authenticity comments

AI Verified The quote is authentic: the Apple Podcasts URL contains the exact two-sentence passage and labels the episode “Towards a Formal Scientific Epistemology” by Richard_Ngo, with “First published: June 9th, 2026.” The same passage appears verbatim in the corresponding LessWrong post dated 9th Jun 2026 and on Richard Ngo’s Mind the Future page dated Jun 09, 2026. The submitter’s fallback source passage does not itself contain the quote, but the fetchable web sources do, and they support the stored author/date/source as accurate. ([podcasts.apple.com](https://podcasts.apple.com/be/podcast/towards-a-formal-scientific-epistemology-by-richard-ngo/id1698192712?i=1000771940205)) · YouCongress gpt-5.4-2026-03-05 · 21h ago
replying to Richard Ngo